{"id":"https://openalex.org/W1996837089","doi":"https://doi.org/10.1109/icassp.2013.6639070","title":"Coupling beamforming with spatial and spectral feature based spectral enhancement and its application to meeting recognition","display_name":"Coupling beamforming with spatial and spectral feature based spectral enhancement and its application to meeting recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1996837089","doi":"https://doi.org/10.1109/icassp.2013.6639070","mag":"1996837089"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041575981","display_name":"Mehrez Souden","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mehrez Souden","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2003","issue":null,"first_page":"7249","last_page":"7253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7883747816085815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423445582389832},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7194994688034058},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6694004535675049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763005018234253},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5638043880462646},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5536879301071167},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5176992416381836},{"id":"https://openalex.org/keywords/coupling","display_name":"Coupling (piping)","score":0.4838317930698395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47994330525398254},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46973690390586853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46283960342407227},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3263527750968933},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2632615268230438},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18378034234046936},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14874103665351868},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09269586205482483}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7883747816085815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423445582389832},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7194994688034058},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6694004535675049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763005018234253},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5638043880462646},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5536879301071167},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5176992416381836},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.4838317930698395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47994330525398254},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46973690390586853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46283960342407227},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3263527750968933},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2632615268230438},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18378034234046936},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14874103665351868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09269586205482483},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W44831635","https://openalex.org/W1952545476","https://openalex.org/W1984196678","https://openalex.org/W1987906574","https://openalex.org/W1989954041","https://openalex.org/W2000431869","https://openalex.org/W2005733316","https://openalex.org/W2018205510","https://openalex.org/W2029564985","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2066218102","https://openalex.org/W2110444924","https://openalex.org/W2127671620","https://openalex.org/W2130432819","https://openalex.org/W2132350316","https://openalex.org/W2138889249","https://openalex.org/W2145563317","https://openalex.org/W2146871184","https://openalex.org/W2162079708","https://openalex.org/W2295905273","https://openalex.org/W4205778870","https://openalex.org/W4247773827","https://openalex.org/W6601563604","https://openalex.org/W6601817925","https://openalex.org/W6640723235"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W2769861442","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W1980506188"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"microphone":[3],"array":[4],"based":[5,16,63],"interference":[6,28,85],"reduction":[7,86],"approaches":[8,69],"for":[9,25],"robust":[10],"automatic":[11],"speech":[12],"recognition.":[13],"A":[14],"model":[15],"multichannel":[17],"spectral":[18,35,111],"enhancement":[19,112],"approach":[20,59],"has":[21],"recently":[22],"been":[23],"proposed":[24,78,91],"effectively":[26],"reducing":[27],"by":[29],"exploiting":[30],"both":[31],"the":[32,38,41,46,67,77,84,90,94,106,117],"spatial":[33],"and":[34,99],"features":[36],"of":[37,43,48,96,108,116],"signals.":[39],"With":[40],"goal":[42],"further":[44],"improving":[45],"effectiveness":[47],"this":[49,58],"approach,":[50],"we":[51],"propose":[52],"a":[53,61,73],"new":[54],"framework":[55,92],"that":[56,101],"combines":[57],"with":[60],"microphone-array":[62],"beamforming":[64,109],"approach.":[65],"Because":[66],"two":[68],"can":[70,81],"work":[71],"in":[72,76,114],"complementary":[74],"manner":[75],"framework,":[79],"they":[80],"greatly":[82],"improve":[83],"performance.":[87],"We":[88],"apply":[89],"to":[93,105],"recognition":[95],"actual":[97],"meetings,":[98],"show":[100],"it":[102],"is":[103],"superior":[104],"use":[107],"or":[110],"alone":[113],"terms":[115],"word":[118],"error":[119],"rates.":[120]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
